System requirements and limitations in AI Desktop Actions

  • Release version: Zurich
  • Updated November 18, 2025
  • 3 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of System requirements and limitations in AI Desktop Actions

    The AI Desktop Actions application enables automation of defined desktop actions created within its Windows application. Understanding the system requirements and limitations is crucial to ensure smooth installation, execution, and reliable automation performance.

    Show full answer Show less

    System requirements

    Hardware: The minimum hardware includes an Intel Core i5 CPU, 4 GB RAM, and at least 20 GB of free disk space post-OS and software installations. The recommended configuration is an Intel Core i7 CPU, 8 GB RAM, and at least 50 GB free disk space.

    Software: The application requires Windows 11, .NET 9.0 runtime and desktop runtime version 9.0.10. No extended monitors should be connected during use.

    User Access and Permissions: Users interacting with the Execution workspace must be added to the Remote Desktop Users group on the target machines and granted Remote Desktop access. When Group Policy is in use, users should be added to an Active Directory group authorized for Remote Desktop access, as local changes to Remote Desktop Users are temporary and can be overridden by Group Policy refreshes.

    Additional Requirements: The theme must be consistent between recording and execution systems. Firewalls must allow bidirectional traffic on ports 80 (HTTP) and 443 (HTTPS), or appropriate custom ports as defined by your IT administrator. Users need full permissions to create and use system I/O communication pipes. The snada:// custom URI protocol should be registered for browser launching of the application if applicable.

    Screen Resolution and Scaling: For automations created before AI Desktop Actions version 1.0.1, screen resolution and scaling must match between recording and execution environments.

    Limitations

    • Parallel Execution: Do not run the AI Desktop Actions Execution workspace simultaneously with RPA Attended Desktop mode to avoid conflicts.
    • Manual Input Handling: Automations requiring manual inputs (e.g., OTP, CAPTCHA) must include explicit instructions for the AI Agent to pause and wait for user input, or else execution will halt.
    • Single Execution: Only one automation can run at a time within the Execution workspace.
    • Screen Element Recognition: Accuracy in auto-assigning screen elements depends on the target application's UI technology and accessibility features. Complex or dynamic UIs may require manual configuration or tuning to improve anchor detection reliability.
    • Table Data Extraction: The "Get Table" step works only if the data is already presented in table format; it does not convert plain text into tables.
    • Browser Usage: Chrome or Edge browsers cannot run in parallel in the main and desktop sessions. Close any browser sessions in the main environment before running automations that use these browsers in the Execution workspace.
    • Sensitive Information: Sensitive data is not masked during recording, so users should avoid capturing sensitive information in recordings.

    Be aware of system requirements and a few limitations when you’re using the AI Desktop Actions application for defined desktop actions.

    Note:
    These system requirements and limitations apply to only defined desktop actions that are created in the AI Desktop Actions Windows application.

    Hardware requirements

    Table 1. Hardware requirements for AI Desktop Actions
    Resource Minimum Recommended
    CPU Intel Processor (Core i5) Intel Processor (Core i7)
    RAM 4-GB RAM 8-GB RAM
    Disk space Minimum 20-GB free disk space after installing the OS, patches, and base software Minimum 50-GB free disk space after installing the OS, patches, and base software

    Software requirements

    • Windows 11 operating system is used.
    • A .NET 9.0 runtime v9.0.10 and .NET 9 Desktop Runtime v9.0.10 is installed.
    • No extended monitors are connected.
    • Add the end users who interact with the Execution workspace of AI Desktop Actions to the Remote Desktop Users group on the target machine and provide Remote Desktop access permissions for seamless automation execution.

      If your organization uses Group Policy, add the end users to a Microsoft Active Directory group that is permitted to use Remote Desktop through Group Policy on each target machine where desktop actions run.

      • Local changes to the Remote Desktop Users group are temporary unless they align with Microsoft Active Directory entitlements.
      • If the user is not entitled, Group Policy refresh automatically removes them from the group.
    • Theme must match between the systems used for recording and execution.
    • Confirm that your firewall allows bidirectional traffic between the AI Desktop Actions application and your ServiceNow instance on the port 80 for HTTP and port 443 for HTTPs.

      If your organization uses non-standard ports for HTTP or HTTPS, confirm the correct ports with your IT administrator before proceeding.

      You must have full permissions to create and use system I/O communication pipes.

    • If applicable, confirm that the snada:// custom URI protocol is registered to launch the AI Desktop Actions application in the browser.
    Note:
    Screen resolution and scaling must be the same between the systems used for recording and execution of desktop actions that are created before AI Desktop Actions v1.0.1.

    Limitations

    Table 2. Limitations with AI Desktop Actions
    Limit Description
    RPA Attended robot and AI Desktop Actions parallel execution

    To avoid conflicts, do not run the AI Desktop Actions Execution workspace and RPA Attended Desktop mode at the same time.
    Pause for human input If your automation requires manual inputs, such as entering an OTP or CAPTCHA, you must provide instructions to the AI Agent to wait for user input during execution. Otherwise, the automation can't proceed.
    Single execution The system supports one automation execution at a time within the Execution workspace.
    Screen elements During recording, auto-assignment accuracy of screen elements depends heavily on the target application’s technology and interface characteristics. Applications with strong accessibility support, such as well-defined UI elements and controls, stable rendering performance, and simple, consistent layouts enable anchors to be detected more reliably. In contrast, UI complexity, such as dynamic elements, frequent layout shifts, animations, or poor accessibility metadata can reduce accuracy and may require manual anchor configuration or additional tuning.
    Getting table information The Get Table step doesn’t convert ordinary text to table data. For the step to capture table data successfully, the data must already be in the table form.
    Browsers parallel execution The Chrome or Edge browser must not be used in parallel in the main session and the desktop session on your system. You must close the session in the main session to execute automations that use the Chrome or Edge browser in the Execution workspace.
    Sensitive information The sensitive information isn’t masked during recording. Confirm that you don’t record any sensitive information.